Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    leave

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     baise
    -0.07
    tracks
    -0.07
     코드
    -0.06
    uye
    -0.06
     billion
    -0.06
    illo
    -0.06
    amo
    -0.06
     قطع
    -0.06
    VERAGE
    -0.06
    enders
    -0.06
    POSITIVE LOGITS
    \Twig
    0.06
    ',{'
    0.06
     cues
    0.06
     Poison
    0.06
    .splitext
    0.06
    (EFFECT
    0.06
    ,[
    0.06
    nell
    0.06
    _penalty
    0.06
    _RX
    0.06
    Act Density 0.009%

    No Known Activations